© 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. 3456
    Prev
    Next
    INDEX
    Explanations

    words related to confrontation or disagreement, expressed through physical actions or speech

    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
    453
    +0.13
    0.4%
    1043
    +0.09
    0.3%
    1183
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1043
    +0.13
    0.06
    2012
    +0.09
    0.05
    613
    +0.09
    0.05
    Negative Logits
     hastened
    -0.77
     impelled
    -0.77
     equalled
    -0.76
     endeavouring
    -0.75
     supposes
    -0.74
     quitted
    -0.73
     engendered
    -0.72
     Achieving
    -0.71
     roused
    -0.70
     pledging
    -0.70
    POSITIVE LOGITS
     credere
    0.96
     trovar
    0.95
     dimenti
    0.94
     vorrei
    0.93
     parlar
    0.93
     imparare
    0.90
     parteci
    0.89
     morire
    0.88
     voglio
    0.87
    ethene
    0.87
    Activations Density 0.266%

    No Known Activations