© 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. 5-GEMMASCOPE-RES-16K
    6. 6440
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers such as case citations and years related to legal contexts

    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
    ))^{
    -0.47
     or
    -0.45
     on
    -0.44
     and
    -0.43
     To
    -0.42
     hữu
    -0.41
    roma
    -0.40
     an
    -0.39
    حوالہ
    -0.39
    hängigkeit
    -0.38
    POSITIVE LOGITS
    Personendaten
    1.36
    expandindo
    1.18
     AttributeSet
    1.03
    ագրություններ
    0.98
    SourceChecksum
    0.97
     myſelf
    0.91
     unknownFields
    0.90
    Diweddarwch
    0.89
     invokingState
    0.88
    EndInit
    0.88
    Activations Density 1.767%

    No Known Activations