© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3303
    Prev
    Next
    INDEX
    Explanations

    terms related to clips and bindings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnknownFieldSet
    -0.89
    NegativeButton
    -0.87
    AndEndTag
    -0.85
    enumii
    -0.83
    antMatchers
    -0.82
    openConnection
    -0.81
    EndInit
    -0.80
    HostException
    -0.79
     NDL
    -0.78
    --}}
    -0.77
    POSITIVE LOGITS
     clip
    2.33
     clips
    2.15
     Clip
    2.11
     Clips
    2.03
    Clip
    1.98
    clip
    1.96
    Clips
    1.78
    clips
    1.78
     clipped
    1.65
     CLIP
    1.62
    Activations Density 0.080%

    No Known Activations