© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 107436
    Prev
    Next
    INDEX
    Explanations

    words related to climbing activities

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

    climbing surfaces

    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
    %%
    
    -0.56
     SRS
    -0.56
    #%%
    
    -0.53
     NCR
    -0.51
     Sangu
    -0.51
     Sox
    -0.51
    tiple
    -0.50
     Dox
    -0.50
     heter
    -0.50
    <h4>
    -0.50
    POSITIVE LOGITS
     climb
    1.89
     Climb
    1.74
     climbing
    1.70
    Climb
    1.69
    climb
    1.64
     Climbing
    1.60
     climbed
    1.59
    Climbing
    1.58
     climbs
    1.56
    climbing
    1.50
    Activations Density 0.003%

    No Known Activations