© 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. 22-GEMMASCOPE-RES-16K
    11. 7546
    Prev
    Next
    INDEX
    Explanations

    numeric data, particularly percentages and age-related information

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

    Numbers followed by math symbols or units of time

    np_acts-logits-general · gemini-2.0-flash

    +, plus, increasing values

    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
    ngdoc
    -0.70
    OGND
    -0.65
    EndGlobalSection
    -0.65
    yntaxException
    -0.62
    SharedDtor
    -0.61
    ⓧ
    -0.60
    inaison
    -0.60
     tartalomajánló
    -0.59
     ISNI
    -0.58
    uxxxx
    -0.57
    POSITIVE LOGITS
    +
    2.02
    +,
    1.75
    +.
    1.73
    +)
    1.69
    plus
    1.60
    +:
    1.58
    +;
    1.49
    +),
    1.45
    +$
    1.44
     plus
    1.41
    Activations Density 0.220%

    No Known Activations