© 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. 5598
    Prev
    Next
    INDEX
    Explanations

    details and actions related to a physical event or situation involving physical harm

    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
    184
    +0.38
    1.4%
    1577
    +0.25
    1.0%
    394
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.38
    0.04
    736
    +0.25
    0.05
    1577
    +0.17
    0.05
    Negative Logits
     gend
    -1.29
     maneu
    -1.26
     lele
    -1.25
     accla
    -1.24
     embra
    -1.24
     alre
    -1.20
     alkoh
    -1.19
     increa
    -1.19
     wien
    -1.18
     Khart
    -1.18
    POSITIVE LOGITS
     onPause
    0.56
    ConstraintMaker
    0.56
    FailureListener
    0.55
     onStop
    0.54
    Hozzáférés
    0.52
     onFailure
    0.52
     inimigos
    0.51
     onSave
    0.48
     kellett
    0.47
    Další
    0.47
    Activations Density 0.307%

    No Known Activations