© 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. 3337
    Prev
    Next
    INDEX
    Explanations

    press releases indicated by the presence of the term "PRWEB"

    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
    1491
    +0.21
    1.0%
    1137
    +0.15
    0.7%
    2011
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1491
    +0.21
    0.03
    1097
    +0.15
    0.04
    1343
    +0.14
    0.04
    Negative Logits
    <bos>
    -0.74
     Cone
    -0.61
    con
    -0.59
    cone
    -0.58
    ContentAlignment
    -0.57
    AccessorTable
    -0.55
     con
    -0.54
     cone
    -0.53
    Cone
    -0.53
     rodillas
    -0.53
    POSITIVE LOGITS
     Kar
    1.38
    Kar
    1.28
    PRWEB
    1.21
     Karsten
    1.17
     KAR
    1.13
     kar
    1.09
     Karla
    1.06
     Julián
    1.03
     Karam
    0.98
     compréhen
    0.96
    Activations Density 0.443%

    No Known Activations