© 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. 1-GEMMASCOPE-RES-16K
    6. 3012
    Prev
    Next
    INDEX
    Explanations

    output statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fubject
    -0.54
     Theſe
    -0.54
     purpoſe
    -0.52
    󠁣
    -0.51
    adpleegd
    -0.51
    ſelves
    -0.50
    RTGC
    -0.50
    Референце
    -0.49
     occafion
    -0.49
    Jeografia
    -0.48
    POSITIVE LOGITS
    host
    0.56
     Pod
    0.54
    Host
    0.53
     للاسماء
    0.52
    Pod
    0.52
     pod
    0.51
     @"
    0.51
     الحره
    0.51
     Host
    0.50
     dude
    0.49
    Activations Density 0.113%

    No Known Activations