© 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. 13918
    Prev
    Next
    INDEX
    Explanations

    locations or objects described in detail with color and motion

    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
    1978
    +0.10
    0.3%
    198
    +0.10
    0.3%
    1129
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1935
    +0.10
    0.04
    1470
    +0.10
    0.04
    198
    +0.10
    0.04
    Negative Logits
    DataPropertyName
    -0.64
    Controllo
    -0.58
    ClientSize
    -0.55
     الحره
    -0.55
     Correlations
    -0.54
     rente
    -0.54
     Asimismo
    -0.54
    Asimismo
    -0.54
    )|^{
    -0.53
    CommandType
    -0.53
    POSITIVE LOGITS
     viciss
    1.13
     fatis
    1.05
     sappi
    1.03
     peculi
    1.02
     scatt
    0.96
     magis
    0.90
     paff
    0.90
     Lycée
    0.87
     Bibl
    0.87
     carrefour
    0.85
    Activations Density 0.364%

    No Known Activations