© 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. 3507
    Prev
    Next
    INDEX
    Explanations

    discussions of diversity and its implications

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

    discourse markers and transition words that signal shifts in narrative or argumentative direction.

    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
     AssemblyVersion
    -0.46
    RTEE
    -0.40
    TestingModule
    -0.40
    RTCK
    -0.40
    transQ
    -0.40
    ->___
    -0.37
    PopMatrix
    -0.37
     hvil
    -0.37
    これからも
    -0.36
     zm
    -0.36
    POSITIVE LOGITS
     honestly
    0.96
    Honestly
    0.93
     Honestly
    0.93
    honestly
    0.86
     frankly
    0.86
     yes
    0.85
    Okay
    0.83
    Yes
    0.83
    Granted
    0.82
    Remember
    0.82
    Activations Density 0.425%

    No Known Activations