© 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. 10-RES-JB
    11. 544
    Prev
    Next
    INDEX
    Explanations

    terms related to attacks or violent events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.27
    1.5%
    1520
    +0.12
    0.7%
    1870
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1520
    +0.27
    0.04
    896
    +0.12
    0.03
    1296
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.23
    JspWriter
    -0.81
    FunctionFlags
    -0.70
    didSet
    -0.70
    else
    -0.67
    displayquote
    -0.67
    RTDA
    -0.65
    ◄
    -0.65
    namespace
    -0.65
    ///**
    -0.64
    POSITIVE LOGITS
     affor
    2.05
     increa
    1.92
     disagre
    1.83
     philanth
    1.82
     strick
    1.80
     stockholm
    1.79
     accla
    1.75
     impra
    1.75
     unwarran
    1.75
     guarante
    1.75
    Activations Density 0.033%

    No Known Activations