© 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. 13850
    Prev
    Next
    INDEX
    Explanations

    content related to products and giveaways

    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
    297
    +0.09
    0.3%
    1177
    +0.09
    0.3%
    1556
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1782
    +0.09
    0.06
    1556
    +0.09
    0.05
    647
    +0.09
    0.03
    Negative Logits
     impon
    -0.82
     utop
    -0.74
     häm
    -0.73
     magazin
    -0.69
     makro
    -0.68
     geolog
    -0.68
     pól
    -0.67
     „,
    -0.65
     ordina
    -0.65
     doveva
    -0.64
    POSITIVE LOGITS
     apiece
    0.69
     totaling
    0.64
    warran
    0.58
     namely
    0.57
     totalling
    0.57
     demurrer
    0.56
    oltán
    0.54
     worth
    0.53
     declaratory
    0.52
    krish
    0.51
    Activations Density 0.339%

    No Known Activations