Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8307
    Prev
    Next
    INDEX
    Explanations

    content related to copyright, licensing, and permissions

    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
    1252
    +0.09
    0.2%
    1897
    +0.08
    0.2%
    185
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    185
    +0.09
    0.03
    958
    +0.08
    0.03
    2001
    +0.08
    0.03
    Negative Logits
     grumbled
    -0.53
     Witkin
    -0.51
    bosky
    -0.51
     shuddered
    -0.50
     murmured
    -0.50
     shivered
    -0.50
     McLaugh
    -0.49
     mumbled
    -0.49
     izvē
    -0.49
     escrever
    -0.49
    POSITIVE LOGITS
     drap
    0.66
     tass
    0.65
     stoff
    0.65
     taz
    0.63
     molle
    0.62
     reser
    0.62
     canne
    0.61
     tred
    0.61
     piaci
    0.60
     copie
    0.60
    Activations Density 0.232%

    No Known Activations