© 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. 14279
    Prev
    Next
    INDEX
    Explanations

    information about individuals and their personal stories

    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
    25
    +0.13
    0.5%
    1573
    +0.13
    0.5%
    1437
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.13
    0.05
    1983
    +0.13
    0.04
    1573
    +0.12
    0.04
    Negative Logits
    Tác
    -0.61
    au
    -0.53
    ++);
    -0.50
    ace
    -0.49
    ain
    -0.48
    Dele
    -0.47
    PD
    -0.46
    bus
    -0.46
    Bộ
    -0.46
    TestMethod
    -0.46
    POSITIVE LOGITS
     carrefour
    0.93
     affez
    0.84
     swarovski
    0.82
     osal
    0.80
     About
    0.80
     about
    0.79
     ABOUT
    0.78
    ABOUT
    0.76
     tenerife
    0.74
     Karang
    0.73
    Activations Density 0.146%

    No Known Activations