© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11257
    Prev
    Next
    INDEX
    Explanations

    program-related terminology and concepts pertaining to treatment strategies in addiction care

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

    Project implementation and partnerships

    np_acts-logits-general · gemini-2.0-flash

    project implementation evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuppressLint
    -0.73
    RequiresApi
    -0.72
     civilisation
    -0.65
     setPassword
    -0.63
    ControllerAdvice
    -0.60
    DebuggerStep
    -0.60
     FetchType
    -0.59
    HasIndex
    -0.58
    xnn
    -0.58
     médical
    -0.56
    POSITIVE LOGITS
     participatory
    0.97
     pilot
    0.87
     project
    0.85
     facilitators
    0.84
     facilitator
    0.80
     stakeholder
    0.79
     facilitation
    0.78
     collaborative
    0.78
     funded
    0.77
     engagement
    0.76
    Activations Density 0.867%

    No Known Activations