© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 439
    Prev
    Next
    INDEX
    Explanations

    personal insights and experiences expressed in a list or narrative format

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

    First-person statements or opinions

    np_acts-logits-general · gemini-2.0-flash

    things to consider

    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
    KommentareTeilen
    -0.58
    ExtendWith
    -0.48
     tương
    -0.47
     gant
    -0.46
     rent
    -0.44
    TestingModule
    -0.43
    кновен
    -0.43
     Threat
    -0.42
     Gründe
    -0.42
     Referential
    -0.42
    POSITIVE LOGITS
     consideration
    0.78
     overlooked
    0.71
     diperhatikan
    0.70
     nakalista
    0.67
     AssemblyVersion
    0.67
     miss
    0.62
     Misses
    0.62
     missed
    0.61
     Consideration
    0.61
    ]--;
    0.60
    Activations Density 0.203%

    No Known Activations