© 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. 8845
    Prev
    Next
    INDEX
    Explanations

    references to military actions and political manipulation

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

    "direct" or "directly" appearing in the text

    np_acts-logits-general · gemini-2.0-flash

    directly

    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
    GraphicsUnit
    -0.65
    tagHelperRunner
    -0.56
    TagHelper
    -0.55
    MockMvc
    -0.53
     >=",
    -0.53
     bezeichneter
    -0.52
     resourceCulture
    -0.51
    migrationBuilder
    -0.50
     habia
    -0.50
    ScopeManager
    -0.50
    POSITIVE LOGITS
     directly
    3.42
     direct
    3.11
    directly
    3.08
     Directly
    2.94
    Direct
    2.78
    direct
    2.74
     directement
    2.71
     Direct
    2.60
     directamente
    2.59
     DIRECT
    2.54
    Activations Density 0.772%

    No Known Activations