© 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. 552
    Prev
    Next
    INDEX
    Explanations

    text related to the importance or necessity of certain actions or decisions

    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
    478
    +0.08
    0.3%
    50
    +0.07
    0.2%
    1363
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    588
    +0.08
    0.03
    1991
    +0.07
    0.03
    1935
    +0.06
    0.03
    Negative Logits
    /***
    -0.95
     intersper
    -0.86
    /*!
    -0.84
    
    -0.82
     /**
    -0.76
    <!--
    -0.75
    ///**
    -0.73
    <bos>
    -0.72
     endow
    -0.70
     ascribe
    -0.68
    POSITIVE LOGITS
     crucial
    1.85
     vital
    1.70
     Crucial
    1.26
    vital
    1.21
     pivotal
    1.21
     vitale
    1.11
    Vital
    1.10
     vitales
    1.09
     Vital
    1.07
     essential
    1.04
    Activations Density 0.135%

    No Known Activations