© 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. 31-GEMMASCOPE-RES-16K
    6. 3448
    Prev
    Next
    INDEX
    Explanations

    references to various sports, particularly football and baseball

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

    the word "football" and related sports terminology.

    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
    omitempty
    -0.39
    ítě
    -0.36
     alimentaria
    -0.35
     būt
    -0.33
     rahat
    -0.33
    JsonProperty
    -0.33
    tispiece
    -0.32
    NamedQueries
    -0.32
     efectivos
    -0.32
     vantagem
    -0.32
    POSITIVE LOGITS
     utafitiHapana
    0.66
    \{\\
    0.59
    valdi
    0.53
     contextLoads
    0.52
    SBATCH
    0.52
     lovers
    0.51
     للمعارف
    0.48
    PerformLayout
    0.48
    EndGlobalSection
    0.48
    хьтан
    0.48
    Activations Density 0.232%

    No Known Activations