© 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. 10852
    Prev
    Next
    INDEX
    Explanations

    mentions of movement or relocation

    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
    1177
    +0.19
    0.6%
    381
    +0.17
    0.5%
    184
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.19
    0.04
    1038
    +0.17
    0.04
    1325
    +0.10
    0.02
    Negative Logits
    .
    -0.65
    <bos>
    -0.60
    .*
    -0.57
    IE
    -0.57
    pm
    -0.57
    *.
    -0.55
    mit
    -0.54
    ().
    -0.54
    TO
    -0.54
    .‏
    -0.53
    POSITIVE LOGITS
     reluct
    1.77
     maneu
    1.76
     shenan
    1.73
     milf
    1.73
     disagre
    1.70
     increa
    1.70
     apprehen
    1.68
     impra
    1.67
     gaily
    1.64
     snoopy
    1.59
    Activations Density 0.515%

    No Known Activations