© 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. 3676
    Prev
    Next
    INDEX
    Explanations

    references to military incidents or operations involving ships or vessels

    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
    1177
    +0.12
    0.3%
    946
    +0.10
    0.3%
    227
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    908
    +0.12
    0.01
    2010
    +0.10
    0.03
    227
    +0.10
    0.03
    Negative Logits
     klap
    -0.62
     moza
    -0.62
     unie
    -0.60
     kask
    -0.59
     meda
    -0.56
     tyn
    -0.53
     etui
    -0.53
     lapto
    -0.52
     pary
    -0.51
    esModule
    -0.51
    POSITIVE LOGITS
     Méndez
    0.91
     hentai
    0.86
     Cárdenas
    0.85
     Viene
    0.81
     shenan
    0.81
     hasbro
    0.80
     Mejía
    0.80
     Darío
    0.79
     Cfr
    0.79
     Marín
    0.79
    Activations Density 0.159%

    No Known Activations