© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15387
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and relationships involving inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accia
    -0.47
     XE
    -0.45
     Administrativna
    -0.45
    ふう
    -0.45
     excu
    -0.42
     enca
    -0.42
     Enroll
    -0.41
    tagHelperRunner
    -0.41
    umab
    -0.41
    Ema
    -0.40
    POSITIVE LOGITS
     >
    0.70
    neq
    0.62
    }>\
    0.61
    geq
    0.60
    leq
    0.57
    supset
    0.57
     }}>
    0.57
     Greater
    0.56
     ponad
    0.56
     than
    0.55
    Activations Density 0.291%

    No Known Activations