© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2393
    Prev
    Next
    INDEX
    Explanations

    terms related to archaeological excavations, detecting errors in programs, and controlling commercial aircraft

    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
    908
    +0.13
    0.4%
    1870
    +0.12
    0.4%
    1842
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    908
    +0.13
    0.06
    1438
    +0.12
    0.05
    136
    +0.12
    0.03
    Negative Logits
     sappi
    -1.50
     alberto
    -1.22
     vorrei
    -1.19
     sergio
    -1.18
     poichè
    -1.18
     dovre
    -1.16
     purtroppo
    -1.16
     voleva
    -1.15
     jorge
    -1.13
     roberto
    -1.10
    POSITIVE LOGITS
    HtmlAttribute
    0.57
    Charsets
    0.56
    :+:
    0.56
    .
    0.54
     such
    0.52
    opsida
    0.51
    ;
    0.50
     unless
    0.50
    ributions
    0.50
     applications
    0.49
    Activations Density 0.577%

    No Known Activations