© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7623
    Prev
    Next
    INDEX
    Explanations

    expressions related to taking specific actions or making decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    597
    +0.14
    0.5%
    1328
    +0.13
    0.5%
    47
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.14
    0.06
    597
    +0.13
    0.06
    1328
    +0.13
    0.05
    Negative Logits
     impelled
    -0.81
     blest
    -0.79
     vainly
    -0.79
     tolerably
    -0.76
     apprehen
    -0.76
     kindled
    -0.75
     withal
    -0.75
     unspeak
    -0.71
     nobly
    -0.70
     perchance
    -0.70
    POSITIVE LOGITS
     OUT
    1.11
    Out
    1.09
    out
    1.04
     Out
    1.04
    OUT
    0.99
     out
    0.94
    outs
    0.91
     outs
    0.89
    getOut
    0.79
    Outs
    0.78
    Activations Density 0.151%

    No Known Activations