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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13137
    Prev
    Next
    INDEX
    Explanations

    locations or settings described as being inside a specific place

    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
    1520
    +0.08
    0.2%
    513
    +0.08
    0.2%
    289
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    513
    +0.08
    0.03
    406
    +0.08
    0.02
    177
    +0.08
    0.03
    Negative Logits
     unspeak
    -0.68
     swee
    -0.68
     gaily
    -0.66
     totalCount
    -0.66
     hairc
    -0.65
     impelled
    -0.63
     responseData
    -0.61
     merrily
    -0.59
     nobly
    -0.59
     minutely
    -0.58
    POSITIVE LOGITS
     pittores
    0.61
    Faites
    0.58
     habang
    0.56
     nõ
    0.56
     Prenez
    0.54
     Dès
    0.54
     Diciembre
    0.54
     Singapur
    0.53
     siyang
    0.53
    født
    0.53
    Activations Density 0.251%

    No Known Activations