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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5375
    Prev
    Next
    INDEX
    Explanations

    information related to software development, including code snippets and API documentation

    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
    876
    +0.23
    0.7%
    678
    +0.15
    0.5%
    394
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.23
    0.07
    876
    +0.15
    -0.00
    309
    +0.12
    0.04
    Negative Logits
     Demokrat
    -0.74
    Rusia
    -0.69
    BASELINE
    -0.69
    Observa
    -0.67
    Método
    -0.67
     bakteri
    -0.67
    </em>
    -0.66
    Imagens
    -0.66
    ++){
    -0.65
    Marshaller
    -0.65
    POSITIVE LOGITS
     compen
    2.22
     increa
    2.18
     effe
    2.17
     affor
    2.17
     inev
    2.13
     nutr
    2.13
     encomp
    2.12
     impra
    2.07
     doman
    2.07
     oner
    2.06
    Activations Density 0.320%

    No Known Activations