© 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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 1043
    Prev
    Next
    INDEX
    Explanations

    Christian religious references, familial relationships and the description of multimedia audio formats

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    728
    +0.10
    0.3%
    882
    +0.09
    0.2%
    1145
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.06
    283
    +0.09
    0.02
    1363
    +0.07
    0.04
    Negative Logits
     impotent
    -0.60
     Sumatera
    -0.60
     ineffectual
    -0.56
     repugnant
    -0.54
     Verenig
    -0.54
     engendered
    -0.53
     impotence
    -0.52
     Warszaw
    -0.52
     bruge
    -0.52
     renounced
    -0.51
    POSITIVE LOGITS
     simplif
    1.37
     quoique
    1.16
     habile
    1.07
     Moderato
    1.06
     sii
    0.99
     buc
    0.99
     leonardo
    0.99
     Hauteur
    0.99
     Longueur
    0.97
     Secrétaire
    0.97
    Activations Density 0.319%

    No Known Activations