© 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. 2403
    Prev
    Next
    INDEX
    Explanations

    resistance or opposition to certain governmental actions or policies

    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
    478
    +0.12
    0.4%
    629
    +0.12
    0.4%
    899
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    629
    +0.12
    0.03
    1557
    +0.12
    0.03
    899
    +0.11
    0.04
    Negative Logits
     encomp
    -0.78
     impelled
    -0.73
     felipe
    -0.72
     apprehen
    -0.72
     ineffec
    -0.71
     unspeak
    -0.71
     javier
    -0.70
     inconce
    -0.68
     jorge
    -0.67
     santiago
    -0.67
    POSITIVE LOGITS
    remain
    0.93
     remain
    0.93
     remained
    0.84
     remains
    0.83
    remains
    0.76
    Remain
    0.73
     Remain
    0.69
    rema
    0.62
     unchanged
    0.62
     stay
    0.60
    Activations Density 0.080%

    No Known Activations