© 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. 12623
    Prev
    Next
    INDEX
    Explanations

    queries and commands related to SQL operations

    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
    RegressionTest
    -0.57
     surla
    -0.54
    colgante
    -0.53
     CreateTagHelper
    -0.53
     CanadaChoose
    -0.50
     AssemblyCulture
    -0.49
    httphttps
    -0.49
     Normdatei
    -0.49
     صوتيه
    -0.47
     doInBackground
    -0.47
    POSITIVE LOGITS
     join
    0.59
     Agg
    0.58
     expressions
    0.57
    Agg
    0.54
     expression
    0.53
    agg
    0.52
    Join
    0.52
    join
    0.52
     agg
    0.52
     JOIN
    0.51
    Activations Density 0.522%

    No Known Activations