© 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. 5354
    Prev
    Next
    INDEX
    Explanations

    approaches and solutions related to problem-solving in various contexts

    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
    872
    +0.11
    0.3%
    1173
    +0.08
    0.2%
    194
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1173
    +0.11
    0.04
    194
    +0.08
    0.03
    451
    +0.08
    0.04
    Negative Logits
     elek
    -0.88
     kram
    -0.83
     hek
    -0.83
     hina
    -0.82
     alp
    -0.80
     Frö
    -0.78
     kug
    -0.78
     bont
    -0.78
     lele
    -0.76
     Somal
    -0.76
    POSITIVE LOGITS
    awsze
    0.75
     involves
    0.65
    jątk
    0.62
     déclarations
    0.61
    dyž
    0.60
    ramienta
    0.57
     leçons
    0.57
    wieś
    0.56
     relates
    0.56
    áklad
    0.56
    Activations Density 0.205%

    No Known Activations