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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3651
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility or necessity

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

    Followed by a form of "be."

    np_acts-logits-general · gemini-2.0-flash

    auxiliary verb followed by verb

    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
     can
    -0.88
    ]--;
    -0.87
    })*/
    -0.75
     will
    -0.72
     often
    -0.66
    ])));
    -0.66
    `;
    
    -0.65
     cannot
    -0.63
    '],$
    -0.62
    /}.
    -0.62
    POSITIVE LOGITS
    IntoConstraints
    0.84
    tagHelperRunner
    0.64
     legyen
    0.62
     whereupon
    0.57
     Ordovician
    0.57
    StoryboardSegue
    0.54
    be
    0.54
     být
    0.53
     initWithFrame
    0.53
    transQ
    0.53
    Activations Density 0.088%

    No Known Activations