© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9362
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to data analysis and reconstruction techniques in research contexts

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

    following verbs of permission/enablement

    np_acts-logits-general · gemini-2.0-flash

    identification and discrimination

    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
    OGND
    -0.47
    Abitanti
    -0.46
    LookAnd
    -0.46
     presentazione
    -0.45
     симпто
    -0.42
    tsch
    -0.42
     preparedness
    -0.41
     Beispiele
    -0.41
     Acceptance
    -0.40
     nouve
    -0.40
    POSITIVE LOGITS
     identification
    1.20
     Identification
    1.08
     identific
    1.06
     identify
    1.04
    Identification
    1.02
     identifying
    0.98
    identi
    0.98
    identify
    0.96
    identification
    0.96
     identifies
    0.96
    Activations Density 1.145%

    No Known Activations