© 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. 13371
    Prev
    Next
    INDEX
    Explanations

    percentage values and numerical proportions

    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
    1042
    +0.14
    0.4%
    674
    +0.12
    0.4%
    1967
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1526
    +0.14
    0.04
    1304
    +0.12
    0.04
    1596
    +0.11
    0.03
    Negative Logits
    futbolista
    -0.62
    comuna
    -0.61
     EEU
    -0.61
    ;;)
    -0.59
    astéro
    -0.56
    álbum
    -0.56
    :,,
    -0.55
    letterSpacing
    -0.55
    LookAnd
    -0.55
    calciatore
    -0.54
    POSITIVE LOGITS
     total
    0.54
     the
    0.52
     what
    0.49
     its
    0.49
    posób
    0.48
     archivio
    0.48
     êtres
    0.47
     their
    0.45
    Total
    0.44
     Total
    0.44
    Activations Density 0.125%

    No Known Activations