© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13788
    Prev
    Next
    INDEX
    Explanations

    quotations or statements attributed to individuals in the text

    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
    521
    +0.15
    0.5%
    663
    +0.14
    0.5%
    228
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.15
    0.05
    228
    +0.14
    0.05
    663
    +0.14
    0.04
    Negative Logits
     kompati
    -0.69
     kristal
    -0.59
    arroll
    -0.58
     silikon
    -0.58
    Matériau
    -0.55
     benzin
    -0.55
     mikrofon
    -0.55
     foton
    -0.54
     maske
    -0.54
     optik
    -0.54
    POSITIVE LOGITS
     reconno
    0.76
     cytoplas
    0.75
     macrop
    0.72
    <bos>
    0.72
     suscep
    0.69
     glau
    0.66
     jacques
    0.65
     says
    0.64
     chromos
    0.64
     olivia
    0.63
    Activations Density 0.112%

    No Known Activations