© 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. 8244
    Prev
    Next
    INDEX
    Explanations

    phrases that evaluate concepts or entities in terms of their definitions or characteristics

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

    "In terms of" or "as far as" phrases

    np_acts-logits-general · gemini-2.0-flash

    in terms of, as far as

    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
     Neglect
    -0.32
     Keluarga
    -0.27
     accompanied
    -0.27
     acquist
    -0.27
    ERÍA
    -0.27
     زه
    -0.27
     carried
    -0.27
    Mon
    -0.26
    IFICACIÓN
    -0.26
     Owner
    -0.25
    POSITIVE LOGITS
     regards
    0.93
     betreft
    0.90
    Concerning
    0.90
    Regarding
    0.88
    regarding
    0.85
     Concerning
    0.81
     Hinsicht
    0.81
     Regarding
    0.81
    rungsseite
    0.79
     regard
    0.77
    Activations Density 0.256%

    No Known Activations