© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4334
    Prev
    Next
    INDEX
    Explanations

    negative and critical sentiments about societal issues and personal challenges

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

    Follows certain adverbs or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    making it seem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.46
    mohonan
    -0.43
    ㊂
    -0.42
    tiérrez
    -0.41
    Aholisi
    -0.40
     houſe
    -0.40
    ngOn
    -0.40
    akaian
    -0.40
     Masyarakat
    -0.39
     Approximate
    -0.39
    POSITIVE LOGITS
    ContentAlignment
    0.60
     calidad
    0.39
    ɵɵelementStart
    0.38
     peggio
    0.37
     Infórmanos
    0.37
    cotta
    0.36
     fibras
    0.36
    SharedDtor
    0.36
    addPreferredGap
    0.35
     szczegól
    0.35
    Activations Density 0.528%

    No Known Activations