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. 9-GEMMASCOPE-RES-16K
    6. 566
    Prev
    Next
    INDEX
    Explanations

    quotes or quotations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inq
    -0.86
     ioutil
    -0.81
     Mait
    -0.78
    ivet
    -0.78
    noopener
    -0.76
     Grot
    -0.76
    Vect
    -0.76
     Sult
    -0.72
     Ves
    -0.72
     Gera
    -0.71
    POSITIVE LOGITS
    ?”
    1.33
    ”
    1.26
    “”
    1.19
    )”
    1.15
    ’”
    1.14
    ?"
    1.11
    !”
    1.10
    }}"
    1.08
    !!”
    1.01
    ,”
    0.99
    Activations Density 0.245%

    No Known Activations