© 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. 3789
    Prev
    Next
    INDEX
    Explanations

    words related to news articles or information

    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
    1870
    +0.11
    0.4%
    1053
    +0.11
    0.4%
    136
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1370
    +0.11
    0.05
    136
    +0.11
    0.03
    1777
    +0.11
    0.04
    Negative Logits
     useRouter
    -0.62
     hek
    -0.57
     mals
    -0.56
     vache
    -0.55
     indeb
    -0.55
     impon
    -0.54
     bergen
    -0.54
     spontan
    -0.54
     diamant
    -0.54
     pép
    -0.53
    POSITIVE LOGITS
     news
    1.32
    news
    1.11
    News
    1.01
     News
    0.99
     NEWS
    0.91
    NEWS
    0.86
     unlaw
    0.77
     tidings
    0.74
    Yess
    0.72
    Xoxo
    0.71
    Activations Density 0.079%

    No Known Activations