Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8027
    Prev
    Next
    INDEX
    Explanations

    phrases related to signal processing and communications

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

    Comes after numerals

    np_acts-logits-general · gemini-2.0-flash

    3rd, numbers, sequencing

    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
     vengan
    -0.39
     llorar
    -0.38
     cruzado
    -0.38
    Síguenos
    -0.35
    ffilm
    -0.35
     guste
    -0.34
     bocca
    -0.34
     pulseras
    -0.34
     privada
    -0.33
     invitado
    -0.33
    POSITIVE LOGITS
    \{\\
    0.70
    TagMode
    0.65
     ब्रेकडाउन
    0.63
     ProtoMessage
    0.59
    ftagPool
    0.57
    ロウィン
    0.55
    stances
    0.55
    EndGlobalSection
    0.53
    enderror
    0.52
     disambiguazione
    0.52
    Activations Density 0.309%

    No Known Activations