© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 1015
    Prev
    Next
    INDEX
    Explanations

    terms related to legal actions and invoking actions

    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
    1363
    +0.12
    0.4%
    58
    +0.12
    0.4%
    78
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1142
    +0.12
    0.02
    1363
    +0.12
    0.03
    78
    +0.12
    0.03
    Negative Logits
     habang
    -0.54
    Analy
    -0.53
     Ajust
    -0.52
     Progres
    -0.51
    ➡
    -0.50
    Addi
    -0.49
    ValueStyle
    -0.49
     Krim
    -0.48
     CEN
    -0.48
     nettement
    -0.47
    POSITIVE LOGITS
     invoke
    0.85
     invokes
    0.77
     invoking
    0.77
     evoke
    0.75
     invoked
    0.75
     evoked
    0.71
     invocation
    0.71
     evokes
    0.69
     Invoke
    0.68
    invoke
    0.67
    Activations Density 0.164%

    No Known Activations