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

    Neuronpedia

    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. 2092
    Prev
    Next
    INDEX
    Explanations

    locations or directions

    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
    964
    +0.09
    0.2%
    1013
    +0.08
    0.2%
    1439
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1680
    +0.09
    0.03
    1216
    +0.08
    0.03
    29
    +0.08
    0.03
    Negative Logits
    łgorzata
    -0.49
    dateTimePicker
    -0.48
     impré
    -0.48
    ohl
    -0.48
     épu
    -0.48
    kese
    -0.46
     Fasc
    -0.46
     incontour
    -0.45
     intermédiaire
    -0.45
     Tapa
    -0.45
    POSITIVE LOGITS
     lamborghini
    0.66
     across
    0.66
     neighbor
    0.65
    across
    0.63
    Across
    0.62
     adjacent
    0.61
     mazda
    0.60
     ACROSS
    0.60
     neighbors
    0.58
     neighboring
    0.58
    Activations Density 0.134%

    No Known Activations