© 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. 14857
    Prev
    Next
    INDEX
    Explanations

    references to events or actions that happened before a certain point in time

    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
    871
    +0.18
    0.6%
    568
    +0.13
    0.5%
    889
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.18
    0.03
    871
    +0.13
    0.02
    1059
    +0.11
    0.02
    Negative Logits
     roh
    -0.45
     Sikhs
    -0.45
     izdel
    -0.43
    ?>">
    -0.41
     kõik
    -0.41
    SceneManagement
    -0.41
     najbol
    -0.41
     hashlib
    -0.40
     rehearing
    -0.39
     kys
    -0.39
    POSITIVE LOGITS
    prior
    0.99
     prior
    0.99
     Prior
    0.96
     PRIOR
    0.94
    Prior
    0.93
     priors
    0.92
    PRIOR
    0.82
     venuto
    0.79
     sentito
    0.78
     affor
    0.75
    Activations Density 0.037%

    No Known Activations