© 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. 2465
    Prev
    Next
    INDEX
    Explanations

    technical strings such as codes or commands

    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
    1343
    +0.35
    1.1%
    876
    +0.16
    0.5%
    924
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.35
    0.04
    924
    +0.16
    0.03
    1476
    +0.09
    0.02
    Negative Logits
     quivering
    -0.66
     impelled
    -0.65
     الاص
    -0.59
     inconceivable
    -0.59
     Констан
    -0.58
     наступ
    -0.57
     some
    -0.56
    بري
    -0.56
     meaningful
    -0.56
     defied
    -0.56
    POSITIVE LOGITS
     illi
    1.35
     dispen
    1.30
     lidl
    1.28
     grati
    1.26
     citoy
    1.24
     effe
    1.24
     noel
    1.23
     coq
    1.23
     desir
    1.23
     oner
    1.22
    Activations Density 0.071%

    No Known Activations