Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6204
    Prev
    Next
    INDEX
    Explanations

    references to methods of identification or matching involving physical characteristics or evidence

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

    Identification or matching of items

    np_acts-logits-general · gemini-2.0-flash

    identification and matching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBOutlet
    -0.48
    cotta
    -0.46
     prospectus
    -0.45
    ########.
    -0.45
    iscus
    -0.44
    execSQL
    -0.43
    ProgressHUD
    -0.43
     عقد
    -0.43
     endfor
    -0.43
    ymce
    -0.43
    POSITIVE LOGITS
     identification
    2.53
     Identification
    2.29
     identify
    2.15
     identifying
    2.14
     identific
    2.13
    Identification
    2.12
     Identi
    2.09
    identi
    2.07
    identification
    2.07
     identi
    2.06
    Activations Density 0.615%

    No Known Activations