© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1062
    Prev
    Next
    INDEX
    Explanations

    keywords related to building instructions or guidelines

    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
    411
    +0.16
    0.6%
    1059
    +0.12
    0.5%
    341
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.16
    0.04
    1059
    +0.12
    0.03
    1492
    +0.11
    0.04
    Negative Logits
     Hancock
    -0.43
     Sou
    -0.42
     Horn
    -0.41
     Nep
    -0.41
    Sou
    -0.41
     Ou
    -0.40
     Cy
    -0.40
     Het
    -0.40
     вашем
    -0.39
    hubaneswar
    -0.39
    POSITIVE LOGITS
    build
    1.23
     Build
    1.22
     build
    1.20
     Builds
    1.20
     BUILD
    1.15
    Build
    1.12
     builds
    1.08
    BUILD
    1.07
    builds
    1.00
     BUILDING
    0.99
    Activations Density 0.065%

    No Known Activations