© 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. 10-GEMMASCOPE-RES-16K
    6. 10486
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive adjectives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.73
    OGND
    -0.61
    extérieur
    -0.52
    ."</
    -0.50
    CommandText
    -0.50
    ]--;
    -0.50
    CompleteListener
    -0.50
    /}.
    -0.49
     ErrIntOverflow
    -0.49
     teasing
    -0.48
    POSITIVE LOGITS
    lalom
    0.77
    databind
    0.68
    ModelForm
    0.68
    AsUp
    0.66
    opold
    0.65
     suyo
    0.64
     nargin
    0.63
    原始内容存档于
    0.62
    BindingResult
    0.62
    coration
    0.62
    Activations Density 0.102%

    No Known Activations