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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15847
    Prev
    Next
    INDEX
    Explanations

    regions, territories, and countries-related 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
    1967
    +0.21
    0.7%
    1741
    +0.11
    0.4%
    1978
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1479
    +0.21
    0.04
    30
    +0.11
    0.04
    1252
    +0.10
    0.04
    Negative Logits
     scrat
    -0.82
     intersper
    -0.80
     shenan
    -0.75
     overcrow
    -0.72
     maneu
    -0.71
     hairc
    -0.71
     disreg
    -0.71
    pozdrawiam
    -0.67
     caress
    -0.65
     impra
    -0.64
    POSITIVE LOGITS
     alkoh
    0.86
     silikon
    0.81
     akut
    0.76
     kompres
    0.76
     kompati
    0.75
     makro
    0.74
     bunda
    0.74
     utop
    0.72
     psychiat
    0.72
    US
    0.72
    Activations Density 0.103%

    No Known Activations