© 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. 20-GEMMASCOPE-RES-16K
    6. 483
    Prev
    Next
    INDEX
    Explanations

    programming constructs and mathematical variables, particularly focusing on identifiers and their properties in code or mathematical expressions

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

    programming and mathematical notation, especially related to variables and pointers in code.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.79
    onViewCreated
    -0.55
    󰀄
    -0.55
    sizeCache
    -0.54
     actionPerformed
    -0.54
    +#+#
    -0.52
    verifyException
    -0.52
    colhead
    -0.51
    ronym
    -0.50
    postsleuth
    -0.50
    POSITIVE LOGITS
    extendable
    0.31
     relating
    0.30
    TabLayout
    0.30
    ❘
    0.29
     сим
    0.26
    EndContext
    0.26
    ByUser
    0.25
     tickets
    0.25
     alone
    0.25
     jugado
    0.24
    Activations Density 0.494%

    No Known Activations