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. 8216
    Prev
    Next
    INDEX
    Explanations

    official titles or positions within organizations

    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
    453
    +0.15
    0.4%
    1177
    +0.14
    0.4%
    227
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.15
    0.04
    752
    +0.14
    0.03
    227
    +0.12
    0.04
    Negative Logits
     purée
    -0.56
     BEHAV
    -0.52
     sprigs
    -0.52
     frites
    -0.51
     jenner
    -0.49
     viewWillAppear
    -0.49
     shallots
    -0.49
     viewDid
    -0.48
     INFLU
    -0.46
     EFFICIENCY
    -0.46
    POSITIVE LOGITS
     destinées
    0.99
     soulign
    0.98
     soigneusement
    0.98
     Cfr
    0.96
     Souha
    0.96
     CiNii
    0.86
     Leurs
    0.86
     Keny
    0.86
    Mə
    0.86
     spécialement
    0.86
    Activations Density 0.162%

    No Known Activations