© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5744
    Prev
    Next
    INDEX
    Explanations

    references to locations, historical events or figures with specific details and dates

    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
    479
    +0.13
    0.6%
    517
    +0.12
    0.6%
    1363
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.13
    0.06
    1741
    +0.12
    -0.01
    478
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.16
     дописавши
    -0.80
    dataclass
    -0.77
    RegistryLite
    -0.74
    舟
    -0.69
    ӣ
    -0.69
    <0xE8>
    -0.67
    dire
    -0.66
    四方
    -0.66
    execSQL
    -0.65
    POSITIVE LOGITS
     unspeak
    1.80
     apprehen
    1.71
     disagre
    1.64
     tolerably
    1.61
     ecru
    1.58
     gaily
    1.57
     depic
    1.57
     reluct
    1.56
     inconce
    1.56
     increa
    1.56
    Activations Density 0.565%

    No Known Activations