© 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. 3315
    Prev
    Next
    INDEX
    Explanations

    mentions of specific social or political topics, such as policy changes, social justice, and political campaigns

    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
    674
    +0.10
    0.3%
    1810
    +0.09
    0.3%
    871
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.10
    0.04
    83
    +0.09
    0.03
    871
    +0.08
    0.03
    Negative Logits
     pylab
    -0.75
     smtplib
    -0.60
     pymysql
    -0.60
     prét
    -0.59
     seaborn
    -0.57
     psycopg
    -0.56
     firent
    -0.56
     skimage
    -0.55
     devaient
    -0.52
     faisaient
    -0.51
    POSITIVE LOGITS
    would
    1.21
     would
    1.20
     WOULD
    1.14
     Would
    1.09
    Would
    1.09
     wouldn
    1.08
    wouldn
    1.04
     wouldnt
    0.99
     Wouldn
    0.86
     could
    0.71
    Activations Density 0.433%

    No Known Activations