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. 17-GEMMASCOPE-RES-16K
    6. 5869
    Prev
    Next
    INDEX
    Explanations

    text related to specific cases or examples pertaining to legal or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GrantedAuthority
    -0.74
    +#+#
    -0.65
    ríamos
    -0.56
    PerformLayout
    -0.55
    ExtendWith
    -0.55
    UrlResolution
    -0.54
    hmig
    -0.53
     nonatomic
    -0.53
    ListItemIcon
    -0.52
    WithMany
    -0.52
    POSITIVE LOGITS
     specific
    2.80
    specific
    2.57
     specifically
    2.52
     particular
    2.50
    Specific
    2.49
     Specific
    2.41
     SPECIFIC
    2.39
     específico
    2.32
    Specifically
    2.31
    particular
    2.25
    Activations Density 0.691%

    No Known Activations