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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 8039
    Prev
    Next
    INDEX
    Explanations

    criticisms related to organization, accountability, and consumer expectations

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

    Expressions of incompetence or disapproval

    np_acts-logits-general · gemini-2.0-flash

    lacking or bad qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Initially
    -0.41
     count
    -0.39
    jom
    -0.39
    Initially
    -0.37
    cta
    -0.36
     getir
    -0.36
     dabei
    -0.35
     viaje
    -0.35
    限定
    -0.34
     ne
    -0.34
    POSITIVE LOGITS
     فريبيس
    1.02
     initComponents
    0.86
     incompetence
    0.85
     الحره
    0.82
     irresponsible
    0.82
     incompetent
    0.81
     tartalomajánló
    0.78
     createSlice
    0.78
    EDEFAULT
    0.78
     صوتيه
    0.78
    Activations Density 0.143%

    No Known Activations