© 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. 35-GEMMASCOPE-RES-16K
    6. 7755
    Prev
    Next
    INDEX
    Explanations

    terms related to paleontology and fossil studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectMocks
    -0.47
    
    -0.43
     Pfarrer
    -0.43
    +#+#
    -0.41
    joso
    -0.40
    oa̍t
    -0.40
     rhestr
    -0.39
    Spectral
    -0.39
    aéroport
    -0.39
    DateTimeField
    -0.39
    POSITIVE LOGITS
     shell
    2.11
     shells
    2.00
    shell
    1.88
     Shell
    1.87
    Shell
    1.74
     Shells
    1.69
    shells
    1.66
     SHELL
    1.66
    SHELL
    1.48
     shellfish
    1.38
    Activations Density 0.336%

    No Known Activations