© 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. 12093
    Prev
    Next
    INDEX
    Explanations

    terms related to software development and coding, with a focus on code modifications and community interactions

    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
    2004
    +0.13
    0.5%
    869
    +0.13
    0.5%
    204
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    869
    +0.13
    0.03
    204
    +0.13
    0.02
    1602
    +0.13
    0.02
    Negative Logits
    StoreMessageInfo
    -0.49
    ếng
    -0.44
     Etrus
    -0.44
     Waltham
    -0.43
    principalColumn
    -0.42
     Albu
    -0.41
    脚注の使い方
    -0.41
     Pierre
    -0.41
    lização
    -0.41
    érfi
    -0.40
    POSITIVE LOGITS
     Mod
    1.41
     mod
    1.39
    Mod
    1.33
    mod
    1.31
     MOD
    1.17
     mods
    1.16
    MOD
    1.12
     Mods
    1.11
    mods
    1.06
     modding
    1.05
    Activations Density 0.069%

    No Known Activations