© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 14871
    Prev
    Next
    INDEX
    Explanations

    chemical species and their reactions involving metals and ions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     kud
    -0.58
    клопе
    -0.57
    Vidite
    -0.57
     intptr
    -0.54
     Margo
    -0.54
     GME
    -0.52
    ocarditis
    -0.52
    RepeatedField
    -0.51
    AutoScaleMode
    -0.51
    inerie
    -0.51
    POSITIVE LOGITS
     ions
    0.72
    ("]");
    0.56
     ion
    0.56
    VIAF
    0.55
    }],
    
    0.52
    transient
    0.52
     oprot
    0.52
    }';
    0.51
     pron
    0.50
    раздо
    0.49
    Activations Density 0.544%

    No Known Activations