© 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. 31-GEMMASCOPE-RES-131K
    6. 110626
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "this" in various contexts

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

    this followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -0.43
     этого
    -0.34
    this
    -0.34
     This
    -0.33
     этом
    -0.32
    This
    -0.32
    interesting
    -0.31
    ungsbedingungen
    -0.30
     này
    -0.30
    green
    -0.29
    POSITIVE LOGITS
    GraphicsUnit
    0.65
    httphttps
    0.61
     unwillingness
    0.60
    RTEX
    0.60
    __':
    
    0.59
     reliance
    0.59
     comunque
    0.58
     protoimpl
    0.58
     reluctance
    0.58
     voglia
    0.57
    Activations Density 0.074%

    No Known Activations