© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14466
    Prev
    Next
    INDEX
    Explanations

    information related to politics and international relations, specifically focusing on conflicts and government 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
    2019
    +0.26
    0.8%
    674
    +0.21
    0.7%
    304
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.26
    0.06
    924
    +0.21
    0.05
    1445
    +0.12
    0.05
    Negative Logits
     CONDUIT
    -0.75
     stickied
    -0.71
     shenan
    -0.71
     Wtf
    -0.70
    Lmfao
    -0.70
     chrysler
    -0.69
    Noice
    -0.67
     downvote
    -0.66
     vagu
    -0.66
     tupperware
    -0.65
    POSITIVE LOGITS
    <bos>
    0.99
    SourceChecksum
    0.76
     termica
    0.73
     Audiodateien
    0.72
     meras
    0.71
     essenziale
    0.70
     eccellente
    0.68
    StoreMessageInfo
    0.68
    ]]>
    0.68
     trasparente
    0.66
    Activations Density 0.243%

    No Known Activations