Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14076
    Prev
    Next
    INDEX
    Explanations

    comparisons in terms of rates and quantities, particularly related to achievements or outcomes

    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
    776
    +0.10
    0.3%
    1385
    +0.09
    0.2%
    1352
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.10
    0.04
    191
    +0.09
    0.02
    1771
    +0.07
    0.03
    Negative Logits
    UIControlState
    -0.56
    iprot
    -0.53
    Datuak
    -0.51
    providedIn
    -0.51
    EFAULT
    -0.50
    InjectMocks
    -0.49
    transQ
    -0.49
    npmjs
    -0.48
    simpleType
    -0.48
    ENOMEM
    -0.48
    POSITIVE LOGITS
     Wtf
    1.00
     Lmao
    0.98
    YMMV
    0.96
     tupperware
    0.94
     ecru
    0.88
     hairc
    0.85
    Fuckin
    0.84
    Wtf
    0.84
     🤣🤣
    0.83
    Noice
    0.81
    Activations Density 0.146%

    No Known Activations