© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4326
    Prev
    Next
    INDEX
    Explanations

    mentions of "wide" in relation to various contexts and items

    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
    481
    +0.15
    0.6%
    75
    +0.11
    0.4%
    1616
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.15
    0.03
    240
    +0.11
    0.03
    1616
    +0.11
    0.03
    Negative Logits
    yticks
    -0.51
     RequestMethod
    -0.48
     pstmt
    -0.47
     kock
    -0.45
    PreAuthorize
    -0.44
    Revenir
    -0.44
    fetchone
    -0.44
    DropColumn
    -0.44
     buk
    -0.43
    FetchType
    -0.43
    POSITIVE LOGITS
     Wide
    1.20
     WIDE
    1.15
     wide
    1.15
    Wide
    1.12
    wide
    1.05
    WIDE
    0.96
    Wider
    0.96
     WID
    0.94
     widen
    0.91
     Wider
    0.91
    Activations Density 0.060%

    No Known Activations