© 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. 2346
    Prev
    Next
    INDEX
    Explanations

    words related to politics and elections

    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
    81
    +0.09
    0.3%
    1551
    +0.08
    0.2%
    1990
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.09
    0.04
    725
    +0.08
    0.03
    1551
    +0.07
    0.04
    Negative Logits
    <bos>
    -0.68
     derselbe
    -0.66
     JULIO
    -0.61
     DIOS
    -0.60
     embodi
    -0.59
     regardant
    -0.58
     pymysql
    -0.57
     felicity
    -0.57
     worin
    -0.56
     vielmehr
    -0.56
    POSITIVE LOGITS
     panik
    0.79
     Nö
    0.76
     akut
    0.75
     makro
    0.74
     bera
    0.73
     Kalifor
    0.73
     Frö
    0.73
     kram
    0.72
     elek
    0.72
     Demok
    0.70
    Activations Density 0.356%

    No Known Activations