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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 14894
    Prev
    Next
    INDEX
    Explanations

    references to sources or origins in scientific contexts

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

    Following prepositions "for," "from," or "of"

    np_acts-logits-general · gemini-2.0-flash

    from, of, for, within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.54
    complexType
    -0.50
    IBOutlet
    -0.48
    </i>
    -0.44
    ")->
    -0.44
    "])
    -0.43
    __.__
    -0.43
    })->
    -0.42
    ])->
    -0.42
     дописавши
    -0.41
    POSITIVE LOGITS
    amaño
    0.76
     TextInputType
    0.72
    เภ
    0.70
    XmlAccessorType
    0.69
    ensburg
    0.66
    YLON
    0.66
    ifikationer
    0.66
     Outros
    0.64
    jmniej
    0.63
    ίδι
    0.62
    Activations Density 0.915%

    No Known Activations