© 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. 22-GEMMASCOPE-RES-16K
    11. 13629
    Prev
    Next
    INDEX
    Explanations

    terms related to outcomes or consequences and their evaluations

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

    "[word] off" or "Off [word]"

    np_acts-logits-general · gemini-2.0-flash

    [something] off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -1.01
     MainAxisSize
    -0.94
     يتيمه
    -0.92
    InitVars
    -0.86
    دانشنامهٔ
    -0.86
    OGND
    -0.82
    BufferException
    -0.80
     AssemblyTitle
    -0.77
    IonicModule
    -0.76
     चीज़ों
    -0.76
    POSITIVE LOGITS
     off
    4.73
    off
    3.77
     Off
    3.72
    Off
    3.67
     OFF
    3.22
    OFF
    2.94
    offs
    2.60
     offs
    2.54
    オフ
    2.43
     オフ
    1.81
    Activations Density 0.509%

    No Known Activations