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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 81837
    Prev
    Next
    INDEX
    Explanations

    references to strength in various contexts

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

    strength

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.57
    MLLoader
    -0.51
     morbid
    -0.50
    principalColumn
    -0.50
    socio
    -0.50
    (['/
    -0.50
     متعلقه
    -0.50
    UnusedPrivate
    -0.50
     dotted
    -0.50
     ducks
    -0.49
    POSITIVE LOGITS
     strength
    1.80
     Strength
    1.70
    Strength
    1.66
    strength
    1.61
     STRENGTH
    1.46
    STRENGTH
    1.25
     strengths
    1.08
     Strengths
    1.03
     Stärke
    1.01
     ſtre
    0.98
    Activations Density 0.008%

    No Known Activations