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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 4039
    Prev
    Next
    INDEX
    Explanations

    phrases and questions related to performance, evaluation, and potential action items in various contexts

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

    Follows punctuation within sentences

    np_acts-logits-general · gemini-2.0-flash

    these, these, these, these

    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
     يتيمه
    -0.44
     &___
    -0.42
     Họ
    -0.38
     voulu
    -0.37
     desselben
    -0.36
    owano
    -0.36
    dieran
    -0.35
     voluto
    -0.35
     aleación
    -0.34
    cemment
    -0.34
    POSITIVE LOGITS
     these
    1.64
    这些
    1.37
    these
    1.35
    これらの
    1.32
    這些
    1.32
     These
    1.31
    These
    1.30
    这一切
    1.25
     THESE
    1.12
     thefe
    1.12
    Activations Density 1.233%

    No Known Activations