© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4027
    Prev
    Next
    INDEX
    Explanations

    financial figures and mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical/scientific notation with symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.58
    千
    -0.50
     }</
    -0.47
    évaluateur
    -0.45
    DispatchToProps
    -0.43
    "}")
    -0.43
     }
    -0.43
    UserScript
    -0.43
     }
    
    -0.42
    haikusbot
    -0.42
    POSITIVE LOGITS
     ſta
    0.48
    Qaeda
    0.45
    цездатний
    0.45
     anſ
    0.44
    uxxxx
    0.43
     chofe
    0.42
    weightedMode
    0.42
     Infór
    0.42
     iſt
    0.41
    AutoScaleMode
    0.41
    Activations Density 0.143%

    No Known Activations