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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 402
    Prev
    Next
    INDEX
    Explanations

    issues that users experienced and may need help with, as well as suggestions for improvements

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.10
    0.4%
    1828
    +0.06
    0.2%
    1919
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.04
    623
    +0.06
    0.03
    825
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.52
    public
    -0.93
    .
    -0.79
    ,
    -0.79
    void
    -0.78
     put
    -0.76
    @
    -0.74
    <eos>
    -0.74
    def
    -0.73
     he
    -0.72
    POSITIVE LOGITS
     maneu
    2.18
     stockholm
    2.12
     fta
    2.06
     eiffel
    2.02
     lamborghini
    1.99
     ftu
    1.98
     increa
    1.97
     affor
    1.97
     accla
    1.97
     scrat
    1.95
    Activations Density 0.074%

    No Known Activations