© 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. 4255
    Prev
    Next
    INDEX
    Explanations

    names of musical artists and bands

    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
    +0.15
    0.5%
    304
    +0.13
    0.4%
    227
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.06
    1152
    +0.13
    0.04
    304
    +0.11
    0.01
    Negative Logits
     report
    -0.64
     kasarigan
    -0.63
     program
    -0.60
    <bos>
    -0.59
     term
    -0.58
     plan
    -0.58
     ten
    -0.58
     no
    -0.57
     zdar
    -0.57
     кон
    -0.57
    POSITIVE LOGITS
     emphat
    1.78
     accla
    1.75
     ?...
    1.63
     !...
    1.59
     embra
    1.58
     indestru
    1.57
     Mlle
    1.57
     hentai
    1.56
     milf
    1.56
     vôtre
    1.50
    Activations Density 0.340%

    No Known Activations