Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8101
    Prev
    Next
    INDEX
    Explanations

    references to games and activities or events happening at a location

    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
    678
    +0.10
    0.3%
    262
    +0.09
    0.3%
    1842
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.10
    0.04
    1369
    +0.09
    0.03
    1551
    +0.09
    0.04
    Negative Logits
     HttpNotFound
    -0.82
     ModelExpression
    -0.68
     المعيارى
    -0.63
     kasarigan
    -0.61
    película
    -0.60
    onViewCreated
    -0.58
     pazi
    -0.58
     izvē
    -0.58
     ļoti
    -0.56
     nepiecieš
    -0.56
    POSITIVE LOGITS
     impra
    0.68
     intersper
    0.67
     indestru
    0.67
     games
    0.66
     unspeak
    0.66
     shenan
    0.66
     frivol
    0.65
     unve
    0.63
     pastime
    0.61
     hairc
    0.60
    Activations Density 0.688%

    No Known Activations