© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13683
    Prev
    Next
    INDEX
    Explanations

    key themes of perseverance, hope, and belief in personal adversity and relationships

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

    "hope" or perseverance

    np_acts-logits-general · gemini-2.0-flash

    hope and persistence

    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
    bootstrapcdn
    -0.53
     OnInit
    -0.47
    proken
    -0.46
     setuptools
    -0.46
     rilass
    -0.44
    internalType
    -0.42
     smoked
    -0.41
    PageRoute
    -0.41
    Planned
    -0.41
    ロウィン
    -0.41
    POSITIVE LOGITS
     persistence
    0.49
     hope
    0.48
     hopeful
    0.46
     Hope
    0.46
     hopes
    0.45
     Persistence
    0.45
     persists
    0.45
     Continuation
    0.44
     espoir
    0.43
    hope
    0.42
    Activations Density 0.345%

    No Known Activations