© 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. 6363
    Prev
    Next
    INDEX
    Explanations

    actions related to taking pictures or selfies

    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
    690
    +0.10
    0.3%
    1018
    +0.10
    0.3%
    1872
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1018
    +0.10
    0.04
    1305
    +0.10
    0.03
    1140
    +0.09
    0.03
    Negative Logits
     jorge
    -1.14
     sergio
    -1.02
     milf
    -1.00
     javier
    -0.97
     alberto
    -0.96
     ricardo
    -0.95
     roberto
    -0.94
     vagu
    -0.93
     peppa
    -0.92
     quoique
    -0.90
    POSITIVE LOGITS
     photograph
    0.71
    <bos>
    0.69
     photos
    0.69
     photographing
    0.68
     photographs
    0.67
     camera
    0.67
     cameras
    0.65
     photographed
    0.65
     capture
    0.65
     photography
    0.64
    Activations Density 0.155%

    No Known Activations