© 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. 14052
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate direction or location changes

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

    "into" followed by an article

    np_acts-logits-general · gemini-2.0-flash

    into [noun phrase]

    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
     âgées
    -0.83
     deschis
    -0.68
     variés
    -0.68
     africains
    -0.67
     correto
    -0.67
     Mesozoic
    -0.64
     înainte
    -0.64
     Balboa
    -0.63
     extérieurs
    -0.62
     declarat
    -0.62
    POSITIVE LOGITS
     the
    1.08
     INTO
    0.91
    INTO
    0.88
    Into
    0.86
     Into
    0.84
     their
    0.79
     ?>/
    0.77
    %");
    0.73
    ]";
    0.73
    "]).
    0.72
    Activations Density 0.078%

    No Known Activations