© 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 EvalsExportsinterp-engineNEWAPI 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. 5018
    Prev
    Next
    INDEX
    Explanations

    mentions of actions related to significant changes or drastic events

    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
    406
    +0.12
    0.4%
    892
    +0.12
    0.4%
    214
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.12
    0.01
    406
    +0.12
    0.01
    1805
    +0.11
    0.01
    Negative Logits
    VisualStudio
    -0.58
    OutputType
    -0.47
    msgid
    -0.46
    iten
    -0.45
    Xna
    -0.45
    Orig
    -0.45
    cassert
    -0.44
    Shrink
    -0.43
    Depend
    -0.43
    glTexCoord
    -0.43
    POSITIVE LOGITS
     sweep
    1.30
     sweeps
    1.23
     swept
    1.20
    sweep
    1.20
     sweeping
    1.17
     Sweep
    1.10
    swept
    0.99
    Sweep
    0.94
    swe
    0.83
     imposs
    0.83
    Activations Density 0.069%

    No Known Activations