© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3803
    Prev
    Next
    INDEX
    Explanations

    names of beer brands and types

    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
    1177
    +0.24
    0.9%
    1343
    +0.18
    0.6%
    50
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1177
    +0.24
    0.04
    981
    +0.18
    0.06
    1343
    +0.12
    0.05
    Negative Logits
    <bos>
    -0.91
    ,
    -0.77
    .
    -0.75
     
    -0.75
     in
    -0.72
     to
    -0.72
     for
    -0.72
     and
    -0.72
     on
    -0.70
    ，
    -0.70
    POSITIVE LOGITS
     alkoh
    1.70
     Kategor
    1.66
     kram
    1.61
     immen
    1.60
     Pièces
    1.60
     kosme
    1.58
     antik
    1.58
     mikrofon
    1.58
     keramik
    1.57
     meis
    1.56
    Activations Density 0.233%

    No Known Activations