© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3662
    Prev
    Next
    INDEX
    Explanations

    statements of existence or non-existence along with related verbs like "is" and "are"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.99
     Administrativna
    -0.90
    ^(@)
    -0.88
     Jefus
    -0.80
     للمعارف
    -0.79
     $_"
    -0.79
     Houſe
    -0.78
    ReusableCell
    -0.75
     NDEBUG
    -0.75
    cuerdo
    -0.74
    POSITIVE LOGITS
    InjectAttribute
    0.72
    <eos>
    0.67
    ↵↵
    0.67
    .
    0.46
    })$.
    0.46
    ]),
    0.44
    努
    0.43
    ↵↵↵↵↵↵↵↵↵
    0.43
    ↵↵↵↵↵↵↵
    0.43
     This
    0.43
    Activations Density 0.467%

    No Known Activations