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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8157
    Prev
    Next
    INDEX
    Explanations

    references to individuals overcoming challenges or adversity

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

    Emotionally resonant words and phrases in narratives about human struggle, achievement, and recognition - particularly terms expressing sentiment, courage, or acknowledgment.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    webElementGuid
    -0.54
     TestBed
    -0.49
     صوتيه
    -0.47
    ">//
    -0.45
    FormTagHelper
    -0.44
    sekten
    -0.42
     للاسماء
    -0.42
    providedIn
    -0.42
     Signalez
    -0.42
     >=",
    -0.41
    POSITIVE LOGITS
    harusnya
    0.51
     sorella
    0.40
     pity
    0.39
     heartbreaking
    0.39
    可怜
    0.38
    tanleria
    0.38
     heartwarming
    0.37
     ConstraintSet
    0.36
     protective
    0.36
     وصلة
    0.35
    Activations Density 0.042%

    No Known Activations