© 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. 584
    Prev
    Next
    INDEX
    Explanations

    locations and addresses in the text

    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
    1624
    +0.09
    0.3%
    50
    +0.09
    0.3%
    765
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    765
    +0.09
    0.03
    1494
    +0.09
    0.03
    1479
    +0.08
    0.02
    Negative Logits
    <bos>
    -0.78
    
    -0.68
    ///**
    -0.60
    Damit
    -0.60
    <?
    -0.59
     inútil
    -0.58
    /***
    -0.58
    var
    -0.57
    public
    -0.56
     continue
    -0.56
    POSITIVE LOGITS
     Des
    2.52
    Des
    2.31
     DES
    2.08
    des
    2.08
     des
    1.96
    DES
    1.88
     desir
    1.82
     unce
    1.53
     fta
    1.51
     unden
    1.49
    Activations Density 0.103%

    No Known Activations