© 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. 4667
    Prev
    Next
    INDEX
    Explanations

    phrases indicating completeness or the presence of all necessary components

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

    "all" or "everything" preceding a statement of necessity

    np_acts-logits-general · gemini-2.0-flash

    everything necessary

    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
    RegressionTest
    -0.43
    DRS
    -0.40
    scriptId
    -0.38
    WriteLiteral
    -0.37
     Patria
    -0.33
    rtz
    -0.33
    centages
    -0.33
    ʺ
    -0.32
    Sprintf
    -0.32
    іод
    -0.32
    POSITIVE LOGITS
     necessary
    1.44
     everything
    1.38
    necessary
    1.30
    everything
    1.27
     needed
    1.27
    Necessary
    1.21
     Necessary
    1.16
    Everything
    1.16
     Everything
    1.14
    needed
    1.13
    Activations Density 0.231%

    No Known Activations