© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12252
    Prev
    Next
    INDEX
    Explanations

    elements and terms related to computer programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msgTypes
    -0.55
    ]]=
    -0.53
    êques
    -0.49
    };*/
    -0.48
    orianCalendar
    -0.46
    ']").
    -0.44
    "}}
    -0.43
    "]]
    -0.43
    ">>
    -0.43
    önen
    -0.42
    POSITIVE LOGITS
     pleaſure
    0.70
    SerializedName
    0.61
     purpoſe
    0.61
     faſt
    0.61
     poffe
    0.61
    WriteBarrier
    0.59
     Efq
    0.58
    <bos>
    0.58
     ſche
    0.58
    δή
    0.57
    Activations Density 0.738%

    No Known Activations