© 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. 18-GEMMASCOPE-RES-16K
    11. 8316
    Prev
    Next
    INDEX
    Explanations

    actions related to activation events or mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a period, or "Weak" / "Weaknesses"

    np_acts-logits-general · gemini-2.0-flash

    actions after a level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PublicKey
    -0.51
    ="@+
    -0.50
    zeera
    -0.48
     collet
    -0.48
     Protobuf
    -0.48
    յ
    -0.46
    omatic
    -0.44
     Cypress
    -0.44
    createQuery
    -0.43
     encor
    -0.42
    POSITIVE LOGITS
     كومونز
    0.56
    WithIOException
    0.56
     feats
    0.55
    feats
    0.54
     stomp
    0.53
    Edited
    0.52
     potrafi
    0.52
    Mismatch
    0.52
    Carriera
    0.50
    InputModule
    0.50
    Activations Density 0.189%

    No Known Activations