© 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. 6-RES-JB
    11. 6450
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to data analysis and computer science

    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
    +0.40
    1.9%
    1842
    +0.13
    0.6%
    1177
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.40
    0.28
    297
    +0.13
    0.14
    1739
    +0.09
    0.10
    Negative Logits
    <bos>
    -2.03
    <eos>
    -0.95
    public
    -0.91
    //
    -0.83
    /*
    -0.82
    def
    -0.81
    else
    -0.79
    @
    -0.77
    class
    -0.77
    void
    -0.76
    POSITIVE LOGITS
     maneu
    2.87
     shenan
    2.75
     affor
    2.73
     accla
    2.70
     disagre
    2.66
     reluct
    2.66
     milf
    2.62
     impra
    2.59
     practition
    2.58
     philanth
    2.57
    Activations Density 12.260%

    No Known Activations