© 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. 14061
    Prev
    Next
    INDEX
    Explanations

    mentions of unspecified items or concepts

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

    mentions of anything or nothing

    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
    Lazy
    -0.42
    |)
    -0.39
    Trie
    -0.38
    PD
    -0.37
    LD
    -0.37
        
    -0.37
    forEach
    -0.36
    fjspx
    -0.36
     verbal
    -0.35
     view
    -0.35
    POSITIVE LOGITS
     anything
    1.48
    anything
    1.40
     nothing
    1.27
     Anything
    1.27
    nothing
    1.25
     ANYTHING
    1.23
    Anything
    1.23
     Nothing
    1.21
     NOTHING
    1.17
    Nothing
    1.16
    Activations Density 0.031%

    No Known Activations