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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14365
    Prev
    Next
    INDEX
    Explanations

    opinions and subjective viewpoints expressed in various contexts

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

    Expressing personal opinions or viewpoints

    np_acts-logits-general · gemini-2.0-flash

    expressing personal opinion

    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
    getColumnIndex
    -0.58
    wakilan
    -0.56
    badlogic
    -0.55
    RectangleBorder
    -0.55
    newswire
    -0.55
    InputBorder
    -0.54
    исленность
    -0.54
    DockStyle
    -0.54
    böz
    -0.54
    dafx
    -0.53
    POSITIVE LOGITS
     IMHO
    1.85
     IMO
    1.81
     imo
    1.76
    IMHO
    1.54
    我认为
    1.44
     me
    1.38
    我觉得
    1.36
    我覺得
    1.32
     Personally
    1.32
     I
    1.30
    Activations Density 0.722%

    No Known Activations