© 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-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4935
    Prev
    Next
    INDEX
    Explanations

    future tense verbs and expressions of obligation or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -0.52
    <?
    -0.49
    stdc
    -0.44
     fubject
    -0.44
     AssemblyTitle
    -0.43
    inferior
    -0.42
    autoFocus
    -0.42
    SENS
    -0.42
    ope
    -0.42
    erba
    -0.42
    POSITIVE LOGITS
     will
    1.22
    will
    1.03
     Will
    1.01
     WILL
    1.01
    Will
    0.99
    WILL
    0.91
     akan
    0.82
     sẽ
    0.82
    จะ
    0.79
     จะ
    0.78
    Activations Density 0.393%

    No Known Activations