© 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. 35-GEMMASCOPE-RES-16K
    6. 7914
    Prev
    Next
    INDEX
    Explanations

    definitions and explanations of concepts related to technology and digital tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.74
     sabotage
    -0.57
     Surprisingly
    -0.54
     Egli
    -0.54
     Visser
    -0.53
     demur
    -0.52
    Дереккөздер
    -0.51
     sobbed
    -0.51
    Surprisingly
    -0.51
     insisting
    -0.51
    POSITIVE LOGITS
    __":
    
    0.56
    enderror
    0.52
    __':
    
    0.51
     fysis
    0.46
     raiſ
    0.45
     validamos
    0.45
    })->
    0.44
     uſed
    0.44
    一群
    0.43
    ChildScrollView
    0.43
    Activations Density 1.201%

    No Known Activations