© 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. 7754
    Prev
    Next
    INDEX
    Explanations

    mentions of political and governmental events or 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
    764
    +0.12
    0.3%
    964
    +0.10
    0.3%
    939
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.12
    0.08
    733
    +0.10
    0.06
    1586
    +0.10
    0.05
    Negative Logits
     kask
    -0.94
     vne
    -0.92
     elek
    -0.92
     traktor
    -0.92
     kram
    -0.92
     stik
    -0.89
     katal
    -0.89
     kras
    -0.89
     karton
    -0.88
     boks
    -0.86
    POSITIVE LOGITS
     its
    0.67
     Its
    0.62
     itself
    0.61
    Its
    0.60
    its
    0.58
     skimage
    0.56
     Itself
    0.55
     OMITBAD
    0.52
    chequer
    0.49
     tetrach
    0.49
    Activations Density 0.888%

    No Known Activations