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. 1-GEMMASCOPE-RES-16K
    6. 15046
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities related to geographical locations and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.82
    tonode
    -0.67
    QMetaType
    -0.60
     invokingState
    -0.59
    cplusplus
    -0.58
    èce
    -0.57
    Portale
    -0.54
    fördert
    -0.54
    Personendaten
    -0.54
    assisted
    -0.53
    POSITIVE LOGITS
     Wy
    0.69
     pond
    0.67
     Lawn
    0.65
     lawn
    0.63
    Pond
    0.62
    Lawn
    0.56
    pond
    0.55
     Pond
    0.55
    SBATCH
    0.54
    KES
    0.54
    Activations Density 2.069%

    No Known Activations