© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 7732
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and specific locations related to historical events, possibly involving conflict or controversy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    0.9%
    82
    +0.09
    0.4%
    893
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1655
    +0.20
    0.03
    977
    +0.09
    0.03
    82
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.82
     дописавши
    -0.70
     CascadeType
    -0.66
    PostInfinity
    -0.65
    <tfoot>
    -0.64
    WriteAttribute
    -0.63
    <tbody>
    -0.62
    BufferException
    -0.62
    AddHtmlAttribute
    -0.61
    },[])
    -0.61
    POSITIVE LOGITS
     quoique
    1.86
     véhic
    1.57
     quelquefois
    1.52
     pratiquement
    1.47
     prouve
    1.44
     renfer
    1.42
     aussitôt
    1.37
     habituellement
    1.35
     prétend
    1.34
     préc
    1.34
    Activations Density 0.061%

    No Known Activations