© 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. 28-GEMMASCOPE-RES-16K
    11. 8448
    Prev
    Next
    INDEX
    Explanations

    terms related to roads and highways

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

    Roadway designations (e.g., I-95, Highway 136)

    np_acts-logits-general · gemini-2.0-flash

    interstate highways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nė
    -0.41
     dAtA
    -0.39
    StructEnd
    -0.38
     ffilmiau
    -0.38
     misura
    -0.37
    horabuena
    -0.37
     ích
    -0.37
     Larsson
    -0.36
    +#+#
    -0.36
     avantages
    -0.35
    POSITIVE LOGITS
     highway
    1.45
     Highway
    1.38
     Hwy
    1.25
     highways
    1.23
    Highway
    1.20
    highway
    1.16
     HIGHWAY
    1.13
     road
    1.08
     Highways
    1.08
     freeway
    1.02
    Activations Density 0.221%

    No Known Activations