© 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. 3919
    Prev
    Next
    INDEX
    Explanations

    critical evaluations and feedback in the context of film and performances

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

    Positive reviews and reception

    np_acts-logits-general · gemini-2.0-flash

    positive reviews and reception

    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
     onCreateView
    -0.55
    ResumeLayout
    -0.49
    Morfo
    -0.48
    uxxxx
    -0.48
     tartalomajánló
    -0.47
    ClientSize
    -0.47
    migrationBuilder
    -0.45
    werbe
    -0.45
    hafter
    -0.45
    igate
    -0.45
    POSITIVE LOGITS
     reviews
    1.56
     critics
    1.55
     praised
    1.43
     praise
    1.43
     Critics
    1.42
     criticism
    1.37
     reviewers
    1.37
     Reviews
    1.32
    Critics
    1.26
     crítica
    1.25
    Activations Density 0.198%

    No Known Activations