© 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. 4-GEMMASCOPE-RES-16K
    6. 15631
    Prev
    Next
    INDEX
    Explanations

    phrases related to the effects or consequences of various factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esine
    -0.71
     TextAppearance
    -0.69
     CreateTagHelper
    -0.68
     skr
    -0.68
     ProtoMessage
    -0.67
    navigationItem
    -0.67
     surla
    -0.67
    Gus
    -0.67
    arz
    -0.66
     authService
    -0.66
    POSITIVE LOGITS
     impact
    2.73
     Impact
    2.58
     impacts
    2.54
    impact
    2.50
     IMPACT
    2.49
     Impacts
    2.41
    Impact
    2.40
    Impacts
    2.36
    IMPACT
    2.30
     impacting
    2.20
    Activations Density 0.075%

    No Known Activations