© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 380
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and object properties

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

    Properties and methods added to objects/nodes

    np_acts-logits-general · gemini-2.0-flash

    invalid or missing properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubourg
    -0.61
    "),
    -0.56
     yyl
    -0.56
     endif
    -0.56
    enaire
    -0.55
    EndGlobalSection
    -0.55
     ";
    -0.55
    labelledby
    -0.54
    ")));
    -0.54
    ")"
    -0.54
    POSITIVE LOGITS
     يتيمه
    0.59
     unregistered
    0.58
     invalid
    0.55
     nonexistent
    0.54
    foo
    0.54
    failing
    0.54
     špat
    0.54
     unclean
    0.54
     inadmissible
    0.53
    Failing
    0.52
    Activations Density 0.276%

    No Known Activations