Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 8656
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to modifications and transformations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dAtA
    -0.74
    DebuggerNonUser
    -0.70
     and
    -0.67
     Efq
    -0.65
     becauſe
    -0.63
     >=",
    -0.63
     Jefus
    -0.63
    ſelves
    -0.61
     houſe
    -0.60
    Personendaten
    -0.59
    POSITIVE LOGITS
    lamide
    0.55
    arkhand
    0.53
    ppas
    0.51
     anschließend
    0.50
    ONESIA
    0.50
     THEN
    0.50
     setName
    0.49
    virons
    0.49
    pelier
    0.49
    apl
    0.49
    Activations Density 0.569%

    No Known Activations