© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3508
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements, particularly in C++ or similar languages

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

    whitespace and indentation tokens, particularly newlines and leading spaces in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextInputType
    -0.77
    EndContext
    -0.67
    PerformLayout
    -0.65
     defaultstate
    -0.60
    outSlope
    -0.60
    SequentialGroup
    -0.60
    PickerController
    -0.59
    bootstrapcdn
    -0.59
     محفوظة
    -0.58
    astéroïdes
    -0.58
    POSITIVE LOGITS
    })();
    0.40
    뀜
    0.38
    There
    0.37
    Refer
    0.36
    Following
    0.36
     Refer
    0.35
     forti
    0.34
    Log
    0.34
    InRange
    0.34
    owy
    0.34
    Activations Density 0.418%

    No Known Activations