© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14134
    Prev
    Next
    INDEX
    Explanations

    references to daily lives and activities of residents in specific areas

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    0.8%
    1577
    +0.19
    0.7%
    599
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.20
    0.12
    1252
    +0.19
    0.09
    1444
    +0.16
    0.06
    Negative Logits
    usermodel
    -0.64
     getNome
    -0.63
    Nhưng
    -0.59
     getNombre
    -0.59
    RectangleBorder
    -0.58
    DataPropertyName
    -0.56
    SizeMode
    -0.55
     FetchType
    -0.55
    PickerController
    -0.54
    ValueGenerated
    -0.54
    POSITIVE LOGITS
     embodi
    1.57
     unwarran
    1.39
     increa
    1.36
     greate
    1.34
     eyel
    1.34
     maneu
    1.34
     suscep
    1.33
     impra
    1.31
     scrat
    1.31
     friable
    1.31
    Activations Density 5.907%

    No Known Activations