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. 8676
    Prev
    Next
    INDEX
    Explanations

    occurrences of error handling or debugging statements in programming code

    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
    4
    -0.54
    PreferredItem
    -0.53
    '
    -0.51
    2
    -0.51
    3
    -0.50
     clear
    -0.49
    5
    -0.48
    1
    -0.46
    9
    -0.45
     (
    -0.45
    POSITIVE LOGITS
    maketitle
    1.22
    bitField
    1.19
    ISupport
    1.17
     nakalista
    1.10
     CreateTagHelper
    1.06
    verwijspagina
    0.99
    AccessorTable
    0.98
    WithIOException
    0.94
    RuleContext
    0.93
    ]")]
    0.93
    Activations Density 0.014%

    No Known Activations