© 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. 1018
    Prev
    Next
    INDEX
    Explanations

    paragraphs containing lists of items or points

    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
    1150
    +0.14
    0.4%
    738
    +0.12
    0.4%
    876
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    792
    +0.14
    0.03
    1816
    +0.12
    0.03
    150
    +0.10
    -0.01
    Negative Logits
     maneu
    -0.73
     venerdì
    -0.69
     bianche
    -0.67
     wien
    -0.66
     ovunque
    -0.65
     poichè
    -0.64
     ohr
    -0.62
     secon
    -0.62
     Heere
    -0.61
     saar
    -0.61
    POSITIVE LOGITS
     corresponding
    1.02
     respective
    0.91
     each
    0.77
    corresponding
    0.76
    each
    0.74
     Corresponding
    0.71
     specific
    0.71
     respectively
    0.71
     соответству
    0.68
     Each
    0.66
    Activations Density 0.627%

    No Known Activations