© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12324
    Prev
    Next
    INDEX
    Explanations

    dates, historical events, and mentions of specific geographical locations or structures

    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
    1741
    +0.12
    0.4%
    1871
    +0.12
    0.4%
    1793
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1793
    +0.12
    0.07
    86
    +0.12
    0.03
    855
    +0.11
    0.05
    Negative Logits
     bono
    -0.73
     مرئيه
    -0.72
     den
    -0.70
    stances
    -0.69
     sie
    -0.68
    mybatisplus
    -0.67
     vor
    -0.67
     dem
    -0.67
     euch
    -0.66
    sertation
    -0.66
    POSITIVE LOGITS
     strick
    2.05
     Mlle
    2.05
     increa
    2.03
     emphat
    2.02
     maneu
    1.96
     accla
    1.95
     perfet
    1.93
     reluct
    1.91
     depic
    1.90
     fuf
    1.90
    Activations Density 0.794%

    No Known Activations