© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8245
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal feelings and relationships

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

    Follows a first-person pronoun or "is"

    np_acts-logits-general · gemini-2.0-flash

    declarative statements expressing belief or preference

    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
     дописавши
    -0.78
     “
    -0.70
     iirc
    -0.65
    ResumeLayout
    -0.60
     bezeichneter
    -0.58
    可谓
    -0.57
     "
    -0.56
    writeFieldEnd
    -0.53
    可以说是
    -0.53
     "":
    -0.52
    POSITIVE LOGITS
     المعيارى
    0.88
    〇〇
    0.77
     here
    0.75
    ○○
    0.75
     XYZ
    0.72
    ◯
    0.71
    StoryboardSegue
    0.69
    !'
    0.67
     blah
    0.67
    ××
    0.67
    Activations Density 0.228%

    No Known Activations