© 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. 8267
    Prev
    Next
    INDEX
    Explanations

    mentions of future plans or intentions

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

    intentions or plans

    np_acts-logits-general · gemini-2.0-flash

    future plans or intentions

    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
    VertexAttrib
    -0.41
     olmaz
    -0.39
    (!__
    -0.37
    iale
    -0.37
     fought
    -0.37
    Pseudo
    -0.36
    BeforeEach
    -0.36
    zijde
    -0.36
    pseudo
    -0.35
     distanciation
    -0.35
    POSITIVE LOGITS
     plans
    1.72
     plan
    1.52
    plans
    1.46
     Plans
    1.45
    Plans
    1.41
     planned
    1.41
     PLANS
    1.37
     intend
    1.35
     intends
    1.34
     plán
    1.31
    Activations Density 0.443%

    No Known Activations