© 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. 4-GEMMASCOPE-RES-16K
    6. 385
    Prev
    Next
    INDEX
    Explanations

    references to fixed values or constants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.80
    InSection
    -0.75
     témo
    -0.72
    FieldDescriptor
    -0.69
    ItemBackground
    -0.69
     <<<<<<<<<<<<<<
    -0.68
    MediaStore
    -0.67
     <=",
    -0.67
    SpringBootTest
    -0.67
    FromArgb
    -0.67
    POSITIVE LOGITS
     Fix
    2.40
     fix
    2.35
    Fix
    2.29
     fixed
    2.27
     Fixed
    2.27
    Fixed
    2.23
    fix
    2.19
     FIXED
    2.16
    fixed
    2.11
     fixes
    2.10
    Activations Density 0.062%

    No Known Activations