© 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. 498
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a conclusion or finding, often related to investigations or reports

    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
    +0.20
    1.4%
    161
    +0.09
    0.6%
    2019
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.20
    0.18
    1350
    +0.09
    0.11
    1187
    +0.08
    0.09
    Negative Logits
    <bos>
    -2.65
    ⓧ
    -1.23
    /**
    -1.14
    <?
    -1.12
    
    -1.05
    /*
    -0.98
    /***
    -0.96
    <?
    -0.88
    ///**
    -0.86
    /*++
    -0.78
    POSITIVE LOGITS
     maneu
    2.04
     accla
    1.88
     affor
    1.84
     impra
    1.82
     increa
    1.82
     disagre
    1.81
     reluct
    1.77
     inev
    1.67
     stockholm
    1.66
     uninten
    1.63
    Activations Density 0.606%

    No Known Activations