Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10615
    Prev
    Next
    INDEX
    Explanations

    code snippets indicating errors or failure in command execution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "exit" and related terms

    np_acts-logits-general · gemini-2.0-flash

    program termination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Référence
    -0.53
    <bos>
    -0.52
    afio
    -0.44
    Referències
    -0.44
    CastException
    -0.41
    $​
    -0.41
    )|\
    -0.40
    tology
    -0.39
    lessness
    -0.39
    IsContent
    -0.39
    POSITIVE LOGITS
    exit
    1.79
     exit
    1.79
     Exit
    1.61
     EXIT
    1.49
    Exit
    1.45
     exits
    1.38
    EXIT
    1.34
     exiting
    1.34
    quit
    1.21
    Exiting
    1.19
    Activations Density 0.149%

    No Known Activations