© 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. 4-GEMMASCOPE-RES-16K
    11. 11337
    Prev
    Next
    INDEX
    Explanations

    rhetorical expressions or phrases that indicate naming or labeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veda
    -0.65
    }}$\\
    -0.64
    PhysRevD
    -0.63
    }));
    -0.63
     ModelExpression
    -0.63
     neceff
    -0.60
    }))
    -0.59
     katze
    -0.59
    AutoresizingMask
    -0.59
     chofe
    -0.58
    POSITIVE LOGITS
    Jereo
    0.65
    lala
    0.57
    ViewFeatures
    0.55
    ksikon
    0.54
    jupiter
    0.52
     pop
    0.52
     pom
    0.51
     NON
    0.51
    contentInset
    0.51
     باخ
    0.50
    Activations Density 1.212%

    No Known Activations