© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14415
    Prev
    Next
    INDEX
    Explanations

    sports-related events and descriptions, particularly those related to wrestling matches and championships

    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
    +0.13
    0.4%
    764
    +0.13
    0.4%
    453
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.13
    0.02
    81
    +0.13
    0.01
    453
    +0.13
    0.04
    Negative Logits
     pollut
    -0.68
     Février
    -0.63
     Décembre
    -0.60
     swarovski
    -0.60
     hansen
    -0.58
     combustibles
    -0.58
     milano
    -0.58
     tricot
    -0.55
    antastic
    -0.54
    uminum
    -0.54
    POSITIVE LOGITS
     kontinu
    0.65
     akut
    0.60
     thereafter
    0.60
     dekoratif
    0.58
     kompati
    0.58
     Rektor
    0.58
     optik
    0.57
     guère
    0.57
     witcher
    0.55
    ghijkl
    0.55
    Activations Density 0.199%

    No Known Activations