© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7278
    Prev
    Next
    INDEX
    Explanations

    phrases related to meeting or fulfilling specific criteria or requirements

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

    Mentions "criteria" or "requirements"

    np_acts-logits-general · gemini-2.0-flash

    criteria and requirements

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    \{\\
    -0.57
    })();
    
    -0.56
    richTextPanel
    -0.54
     ChromeDriver
    -0.51
    ↹
    -0.50
     RIPRODUZIONE
    -0.47
     ©️
    -0.47
    WriteBarrier
    -0.47
    intenant
    -0.46
    transQ
    -0.46
    POSITIVE LOGITS
     criteria
    1.46
     Criteria
    1.39
    Criteria
    1.30
    criteria
    1.23
     CRITERIA
    1.21
     Kriterien
    1.19
     criterion
    1.16
     critères
    1.16
     criter
    1.02
     Criterion
    0.92
    Activations Density 0.740%

    No Known Activations