Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 6959
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.94
    ⤹
    -0.91
     surla
    -0.90
    ScopeManager
    -0.86
     Италијани
    -0.86
    GOTREF
    -0.85
     propOrder
    -0.85
    webElementXpaths
    -0.85
    oa̍t
    -0.84
    Rhestr
    -0.82
    POSITIVE LOGITS
    1
    0.31
     
    0.31
    2
    0.29
    ,
    0.29
    ),
    0.28
    },
    0.27
    6
    0.27
    );
    0.27
    5
    0.27
    9
    0.27
    Activations Density 2.338%

    No Known Activations